Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

external supervisor

Sarah Walker, Professor of Statistics and Epidemiology, Nuffield Department of Medicine

BACKGROUND

Infections pose a major risk to health globally, and also in the UK where they are responsible for 7% of deaths, 21% of all workdays lost, and cost £30bn a year. Antimicrobial resistance (AMR) threatens effective treatment of infection and healthcare associated infections (HCAIs) impact 1 million people each year in the UK.

Advances in data availability and new artificial intelligence (AI) methods offer the chance to develop:

  • more responsive, comprehensive, and automated HCAI/AMR surveillance generating better breadth and depth of intelligence to drive action and changes in practice to protect diverse populations at local, regional, and national levels
  • predictive tools to improve care of individual patients and combat AMR
  • methods, infrastructure and skills to optimally use rapidly-evolving electronic healthcare record and patient-contributed data, and emerging AI technologies.

RESEARCH EXPERIENCE, RESEARCH METHODS AND TRAINING

Several possible specific projects are available, including:

  • developing/testing automated electronic surveillance approaches for rapidly detecting changes in infections and identifying at-risk populations; and deploying these tools in hospitals and national systems
  • extending and piloting in the NHS predictions of personal AMR risk to optimise infection treatment, prevention and control, developing generalisable methods that can update over time/to new locations, and approaches for safely implementing them
  • pre-emptive surveillance, investigating which metrics of hospital processes (e.g. isolation/screening/diagnostic use/cleaning) are associated with HCAI/AMR to inform prevention.

Related projects can also be developed, please contact David Eyre.

Large-scale comprehensive healthcare data are available, including a highly-detailed clinical dataset from 1% of the UK population spanning over 10 years. There will also be opportunities for working with national data and combined community/hospital data from whole UK regions.

The candidate will learn a wide range of state of the art statistical and machine learning approaches, based in the Big Data Institute within a broad infection research consortium.

FIELD WORK, SECONDMENTS, INDUSTRY PLACEMENTS AND TRAINING

The DPhil will involve working closely with the UK’s national public health agency, UKHSA, as well as NHS hospitals, clinicians and other healthcare providers. Industry partnerships to further develop successful tools and approaches will be supported by close working with the University’s technology transfer organisation – Oxford University Innovation.

PROSPECTIVE  STUDENT

The ideal candidate would like solving real-world applied problems that matter and are also technically exciting and challenging. They should have excellent computational and numerical skills (although competence in specific techniques or healthcare experience is not a prerequisite). Someone who also feels at home in a welcoming, enthusiastic, and multidisciplinary team will thrive in this DPhil.

Supervisor